Vision Sensor-Based Road Detection for Field Robot Navigation

Lu, Keyu; Li, Jian; An, Xiangjing; He, Hangen

doi:10.3390/s151129594

Cited by 24 publications

(23 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For some applications, boundary adherence is the most important property for superpixels; whereas for some other applications, more regular shapes may be preferable, such as in [29,30]. Hence, for most of superpixel algorithms, such as [26,35,37], etc., the ability to control this tradeoff is their important property.…”

Section: Methodsmentioning

confidence: 99%

Local Competition-Based Superpixel Segmentation Algorithm in Remote Sensing

Liu

Tang

2017

Sensors

View full text Add to dashboard Cite

Remote sensing technologies have been widely applied in urban environments’ monitoring, synthesis and modeling. Incorporating spatial information in perceptually coherent regions, superpixel-based approaches can effectively eliminate the “salt and pepper” phenomenon which is common in pixel-wise approaches. Compared with fixed-size windows, superpixels have adaptive sizes and shapes for different spatial structures. Moreover, superpixel-based algorithms can significantly improve computational efficiency owing to the greatly reduced number of image primitives. Hence, the superpixel algorithm, as a preprocessing technique, is more and more popularly used in remote sensing and many other fields. In this paper, we propose a superpixel segmentation algorithm called Superpixel Segmentation with Local Competition (SSLC), which utilizes a local competition mechanism to construct energy terms and label pixels. The local competition mechanism leads to energy terms locality and relativity, and thus, the proposed algorithm is less sensitive to the diversity of image content and scene layout. Consequently, SSLC could achieve consistent performance in different image regions. In addition, the Probability Density Function (PDF), which is estimated by Kernel Density Estimation (KDE) with the Gaussian kernel, is introduced to describe the color distribution of superpixels as a more sophisticated and accurate measure. To reduce computational complexity, a boundary optimization framework is introduced to only handle boundary pixels instead of the whole image. We conduct experiments to benchmark the proposed algorithm with the other state-of-the-art ones on the Berkeley Segmentation Dataset (BSD) and remote sensing images. Results demonstrate that the SSLC algorithm yields the best overall performance, while the computation time-efficiency is still competitive.

show abstract

Section: Methodsmentioning

confidence: 99%

Local Competition-Based Superpixel Segmentation Algorithm in Remote Sensing

Liu

Tang

2017

Sensors

View full text Add to dashboard Cite

show abstract

“…The Graph label method [19] is based on label transfer and, uses an approximate nearest neighbor algorithm. In the GrowCut framework [35], the superpixel-level seeds are selected using an unsupervised way, and the superpixel neighbors are detected. The Superpixel-based conditional random field (SCRF) method [17] regularizes a classifier by aggregating histograms in the superpixel neighborhoods, and apply a conditional random filed model for refinement.…”

Section: Road Detection Experimentsmentioning

confidence: 99%

Spatiotemporal road scene reconstruction using superpixel-based Markov random field

Liu

Zhu

et al. 2020

Information Sciences

View full text Add to dashboard Cite

“…The methods based on the understanding of the image geometry usually extract some high-level features which can describe the geometry of the road like the vanishing point [8,11,16,21] and the horizon line [11,18,19,20], and then estimate the range of the road region. These abstract features are extracted through the analysis of the low-level information and their accuracies are susceptible to the details of the image.…”

Section: Introductionmentioning

confidence: 99%